Performance Evaluation of Lightweight Face Detection Models on Low-Resolution Images
Bibliographic record
Abstract
ObjectivesThis study evaluates the detection accuracy of lightweight face detection models on low-resolution images, focusing on their feasibility for edge devices with limited computational resources.To understand the background of this research, it is essential to consider the growing demand for implementing machine learning functionalities, such as image recognition, on edge devices positioned at the network edge, like communication robots and surveillance cameras.Privacy is a critical concern for devices installed in domestic environments.For instance, when using the camera on a communication robot to estimate indoor conditions, low-resolution images, such as mosaics, are preferred for tasks like face detection that do not require identifying individuals.However, performing machine learning tasks such as object detection on images often relies on computationally intensive deep learning methods.Edge devices, with their limited computational resources, require simpler and more lightweight models.This study evaluates the detection accuracy of lightweight face detection models for low-resolution images.Lightweight models are expected to have limitations in detection accuracy.However, this research compares the accuracy of these models to that of conventional advanced deep learning models run on cloud servers.Specifically, we investigate whether lightweight models can achieve detection accuracy comparable to conventional models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".